Improving Efficiency in Convolutional Neural Network with Multilinear Filters
This work addresses efficiency issues in deep learning for applications like autonomous devices, but it is incremental as it builds on existing CNN principles with a novel layer design.
The authors tackled the problem of high memory and computational costs in deep neural networks by proposing a new neural network layer structure using multilinear projection as the primary feature extractor, which requires several times less memory than traditional CNNs and outperforms them while using far fewer parameters.
The excellent performance of deep neural networks has enabled us to solve several automatization problems, opening an era of autonomous devices. However, current deep net architectures are heavy with millions of parameters and require billions of floating point operations. Several works have been developed to compress a pre-trained deep network to reduce memory footprint and, possibly, computation. Instead of compressing a pre-trained network, in this work, we propose a generic neural network layer structure employing multilinear projection as the primary feature extractor. The proposed architecture requires several times less memory as compared to the traditional Convolutional Neural Networks (CNN), while inherits the similar design principles of a CNN. In addition, the proposed architecture is equipped with two computation schemes that enable computation reduction or scalability. Experimental results show the effectiveness of our compact projection that outperforms traditional CNN, while requiring far fewer parameters.